© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112417
    Prev
    Next
    INDEX
    Explanations

    code comments and file headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rescue
    -0.11
    oved
    -0.10
     resc
    -0.10
     rescue
    -0.10
     laten
    -0.10
     resh
    -0.10
     exceedingly
    -0.09
    ér
    -0.09
     devel
    -0.09
    engl
    -0.09
    POSITIVE LOGITS
     Gü
    0.09
     Strip
    0.09
     strip
    0.08
     sach
    0.08
     Crab
    0.08
    Strip
    0.08
     closely
    0.08
    ieri
    0.08
     Cum
    0.08
     Sak
    0.08
    Activations Density 0.002%

    No Known Activations